3 papers
cs.AI2026
A Four-Stage Decomposition of Word-Problem Solving and Mechanistic Fragility in LLM Math Reasoning
Zhongdi Qu, Carla P. Gomes
Large language models solve grade-school math word problems with high accuracy, yet a single irrelevant clause inserted into the problem can collapse it. We reconcile these observa…
cs.CL2024
GEM-RAG: Graphical Eigen Memories For Retrieval Augmented Generation
Brendan Hogan Rappazzo, Yingheng Wang, Aaron Ferber +1
The ability to form, retrieve, and reason about memories in response to stimuli serves as the cornerstone for general intelligence - shaping entities capable of learning, adaptatio…
cs.CV2024
Critic Loss for Image Classification
Brendan Hogan Rappazzo, Aaron Ferber, Carla Gomes
Modern neural network classifiers achieve remarkable performance across a variety of tasks; however, they frequently exhibit overconfidence in their predictions due to the cross-en…